Pith. sign in

Paper Citation Record · LEDGER

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL

As of 12 August 2026, this Paper Citation Record lists 87 of 87 outbound references and 7 inbound Pith citation observations for arXiv:2602.22190.

A citation records a reference. It does not transfer a finding from one paper to another.

pith.paper-citation-record.v1
2602.22190 v2

Coverage vector

measured 87 of 87 reference resolution

Typed states for the displayed outbound observations.

Source: paper_references, paper_reference_links, observed 2026-08-02T20:51:47.961506Z

measured 94 of 94 standing notices

One-hop event checks from named stored sources.

Source: scholarly_work_events, retraction_status_cache, observed 2026-08-12T06:34:41.77262+00:00

measured 7 of 7 inbound itemization

Pith citing papers itemized under the disclosed page cap.

Source: paper_references, paper_reference_links, observed 2026-08-12T00:44:22.198316Z

measured 0 of 1 external citation measurements

A source-named dated measurement, never combined with another source.

Source: pith, observed 2026-07-02T11:56:55.516310Z

Reference resolution

87 of 87 outbound references displayed

  • verified exact0
  • verified fuzzy0
  • unresolved86
  • parse uncertain0
  • malformed identifier1
  • metadata mismatch0

External citation measurements

No source-named external measurement is stored.

Outbound references

Observation 6e652f09-70b4-4a49-b1e7-7cb17d8fa838 · outbound

This paper cites write newline.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL write newline

Reference 1

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:39.595656Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:39.595656Z digest=sha256:d6b9566651da2995efb5135431bba992c952cd61712cfa05fa397317bcf61456

Observation 7ac63f35-e942-4b1f-9f78-7f71e6c7672c · outbound

This paper cites Fara-7b: An efficient agentic model for computer use.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Fara-7b: An efficient agentic model for computer use

Reference 2

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:39.708849Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:39.708849Z digest=sha256:dc4ba281433411d8168d0fcb7d511bd2114eabb5c90af86dec49e149cdedcbd6

Observation b1c178a9-2be6-437b-8364-fb11b1d6718e · outbound

This paper cites Uibert: Learning generic multimodal representations for ui understanding, 2021.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Uibert: Learning generic multimodal representations for ui understanding, 2021

Reference 3

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:39.896351Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:39.896351Z digest=sha256:325951b3565c8322a0545274b542f231ce00e232cf3d96d484584800f5b6220b

Observation 355963d0-0bc2-43bb-bc9d-3e7e4c12e1b3 · outbound

This paper cites DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL DigiRL: Training In-The-Wild Device-Control Agents with Autonomous Reinforcement Learning

Reference 4

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:40.057308Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:40.057308Z digest=sha256:a18da47d2f139f7ab4b99fbf3c1d30886831bedfc066e33cf364ee48e7d349b5

Observation 60d5b548-a1e9-4fd9-bf11-087dc2abab76 · outbound

This paper cites Digi RL : Training in-the-wild device-control agents with autonomous reinforcement learning.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Digi RL : Training in-the-wild device-control agents with autonomous reinforcement learning

Reference 5

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:40.200478Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:40.200478Z digest=sha256:c61b0f723ea782ffcdaf6e5fe8f7a6dba47deabd661cde874e2d914468079773

Observation 14477464-be96-4e64-bc0c-b0d5824c1522 · outbound

This paper cites WebGym: Scaling Training Environments for Visual Web Agents with Realistic Tasks.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL WebGym: Scaling Training Environments for Visual Web Agents with Realistic Tasks

Reference 6

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:40.280648Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:40.280648Z digest=sha256:3fdda169b9030899e370a2f0a27d1013885b0f535b6b00eea277ed304d0b4258

Observation d7567fb1-0730-4be7-9d34-20a5cd28eb33 · outbound

This paper cites Qwen3-VL Technical Report.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Qwen3-VL Technical Report

Reference 7

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:40.372101Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:40.372101Z digest=sha256:02f645dcd5246538e399b55f8b3ea4372e4474229c541192a6b16e6e6d396a7f

Observation 7c582dfa-54e1-40a1-a126-7e89b29eb21e · outbound

This paper cites Qwen2.5-VL Technical Report.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Qwen2.5-VL Technical Report

Reference 8

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:40.488176Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:40.488176Z digest=sha256:2f187a0727ea8ef1961e33e7ec28dc13db6f5ee11a9f3ce1a05bed35628b8850

Observation c857417a-9d2d-43ac-a66c-f06399a13159 · outbound

This paper cites AMEX : Android multi-annotation expo dataset for mobile GUI agents.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL AMEX : Android multi-annotation expo dataset for mobile GUI agents

Reference 9

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:40.581302Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:40.581302Z digest=sha256:d6f610a6daff89118ed528fe8e78f3cad8d548c56511acf538bac44e6e8d416f

Observation 5777b625-f567-48e8-842c-40724e527394 · outbound

This paper cites Era: Transforming vlms into embodied agents via embodied prior learning and online reinforcement learning, 2025 a.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Era: Transforming vlms into embodied agents via embodied prior learning and online reinforcement learning, 2025 a

Reference 10

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:40.647987Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:40.647987Z digest=sha256:8d192a99462086d90a0d5e3162f0abf88caaaf29094496f127978872adb04d20

Observation 10ac2ed4-47a0-4554-ac3e-70870feb4fa7 · outbound

This paper cites Ui-ins: Enhancing gui grounding with multi-perspective instruction-as-reasoning, 2025 b.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Ui-ins: Enhancing gui grounding with multi-perspective instruction-as-reasoning, 2025 b

Reference 11

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:40.741233Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:40.741233Z digest=sha256:cf89a90d0af4286ed0e37351b1d26669c9484c47b193a4d74d95d3b6873f248b

Observation 927b800c-f6d0-43d5-847f-e2e8e19021d9 · outbound

This paper cites GUIC ourse: From general vision language model to versatile GUI agent.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL GUIC ourse: From general vision language model to versatile GUI agent

Reference 12

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:40.835625Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:40.835625Z digest=sha256:85b659522dd690a3e6502b72cfe21ea7272d3912caf75e557674342efd08b4ae

Observation f1648194-23de-4384-ba6b-b7c21a3cf6ff · outbound

This paper cites SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents

Reference 13

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:40.935767Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:40.935767Z digest=sha256:9de4021caeddceca7f1c334c0662d880e22d9095e41a0468f87a34c8b30d9618

Observation 9e6de960-4f6c-490b-86f2-932687d6ce92 · outbound

This paper cites S ee C lick: Harnessing GUI grounding for advanced visual GUI agents.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL S ee C lick: Harnessing GUI grounding for advanced visual GUI agents

Reference 14

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:41.022179Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:41.022179Z digest=sha256:7ea326e239418ee03a0320ea82abe05ede13f1f40116359144def8178ccdb013

Observation 8f38b1a0-e82a-4749-9870-f37d6e5c5971 · outbound

This paper cites Rico: A mobile app dataset for building data-driven design applications.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Rico: A mobile app dataset for building data-driven design applications

Reference 15

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:41.088334Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:41.088334Z digest=sha256:4095bd9f46d1b9a160700f6413ab72ab21ec454d6b4fb918fb6a146718eb8b47

Observation 1ae8b9fe-3c6b-42d9-bc1d-7f0c3bb717c8 · outbound

This paper cites Mind2web: Towards a generalist agent for the web.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Mind2web: Towards a generalist agent for the web

Reference 16

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:41.153829Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:41.153829Z digest=sha256:269f854dcf49a470d1d07b210b57441fec0611347e9e52b3b7f732451db54b22

Observation c3eecac9-0ddd-4fcf-830f-3c61b57818c4 · outbound

This paper cites OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles

Reference 17

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:41.234653Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:41.234653Z digest=sha256:75d257fb44e8f915c0bbe30f02bec2d8e34df90f0d075807d4d208c7bf55986e

Observation d6afb091-cd27-4c5b-8c3f-9224b83ddbcb · outbound

This paper cites Group-in-Group Policy Optimization for LLM Agent Training.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Group-in-Group Policy Optimization for LLM Agent Training

Reference 18

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:41.334848Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:41.334848Z digest=sha256:3148e3c7e1686c18598e3e33347007758271c3cd5ca00f82bc5a698dab1a0fe0

Observation f82b00b0-b0de-45d7-b018-ccbbc6336f52 · outbound

This paper cites Scaling laws for reward model overoptimization.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Scaling laws for reward model overoptimization

Reference 19

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:41.406160Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:41.406160Z digest=sha256:b73626cc670e309cf3280139c41ba014bec322645cb613ee0008072c2a046976

Observation ca6930ee-f58a-4fc0-8047-0d3560597122 · outbound

This paper cites Navigating the digital world as humans do: Universal visual grounding for GUI agents.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Navigating the digital world as humans do: Universal visual grounding for GUI agents

Reference 20

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:41.470504Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:41.470504Z digest=sha256:326c352a4ce69f33504e8831938374850cef892293b2cdfe3cbb6c9751eddf1b

Observation 38469782-6ce8-473b-a51a-60378d397cec · outbound

This paper cites UI-Venus Technical Report: Building High-performance UI Agents with RFT.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL UI-Venus Technical Report: Building High-performance UI Agents with RFT

Reference 21

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:41.570164Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:41.570164Z digest=sha256:a8b294163b9f7f0a7c526a7a9610425086eec9572cc4fe7f27d36aa9d98f47ed

Observation 66b7ce4b-2806-4ecb-acfd-e2a20e8e9621 · outbound

This paper cites Scalable data synthesis for computer use agents with step-level filtering.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Scalable data synthesis for computer use agents with step-level filtering

Reference 22

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:41.626666Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:41.626666Z digest=sha256:1985e5878d97f4635871201b2403871753ec4a13e8f4fa1d9f4bef40d0672b61

Observation 21f88a99-059f-476c-b015-b335f9e403b8 · outbound

This paper cites Cogagent: A visual language model for gui agents, 2023.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Cogagent: A visual language model for gui agents, 2023

Reference 23

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:41.709616Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:41.709616Z digest=sha256:e3683e08703005bfc47a704a63e53722672ed059e943a5c55d173c5fee0862e7

Observation 0ed4a0e8-0cda-4841-95b3-4d180ee4915f · outbound

This paper cites CogAgent: A Visual Language Model for GUI Agents.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL CogAgent: A Visual Language Model for GUI Agents

Reference 24

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:41.781289Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:41.781289Z digest=sha256:28969c0ecb5e656a22eb0de3dd82a257b923fab969cbf74c0a65f067c952123e

Observation 23d1880b-e77c-4be0-8565-7b374eecc4eb · outbound

This paper cites GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL GLM-4.5V and GLM-4.1V-Thinking: Towards Versatile Multimodal Reasoning with Scalable Reinforcement Learning

Reference 25

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:41.856269Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:41.856269Z digest=sha256:703e01942848e2208eeefe72f710d423de574c52898da51ebabfc699a98bc43c

Observation 3b6e6c30-575f-44e9-a0b2-21e30ef67aa6 · outbound

This paper cites Screenspot-pro: Gui grounding for professional high-resolution computer use.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Screenspot-pro: Gui grounding for professional high-resolution computer use

Reference 26

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:41.937161Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:41.937161Z digest=sha256:ec0d069f9c3ccc317ca43c22df25d93b0093b7a144850fcb8d0fc40d106ee2cc

Observation b414e4b6-5452-4ab6-aac6-b2fecedcc055 · outbound

This paper cites On the effects of data scale on UI control agents.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL On the effects of data scale on UI control agents

Reference 27

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:42.020689Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:42.020689Z digest=sha256:b9096bf6264676fcae38a69123ec1ba0710aedc62ea01e35c09a135eae27ae79

Observation 3065b7c4-c6a2-4c9f-99a5-7be335d83ecf · outbound

This paper cites Mapping natural language instructions to mobile UI action sequences.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Mapping natural language instructions to mobile UI action sequences

Reference 28

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:42.119885Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:42.119885Z digest=sha256:9287afdd10a43192a423231712be048fc141cd00b233363ca9f7045e85f89138

Observation ae98de42-a5a8-4d76-905b-01a24ea2be5a · outbound

This paper cites Widget captioning: Generating natural language description for mobile user interface elements.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Widget captioning: Generating natural language description for mobile user interface elements

Reference 29

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:42.196640Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:42.196640Z digest=sha256:89ecf38913beedb04d12e5826e7aed6d44285322c15b1ba45e6906c76ddb9755

Observation 37e5ef16-a407-4fb9-bb37-3c778e521058 · outbound

This paper cites ShowUI: One Vision-Language-Action Model for GUI Visual Agent.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL ShowUI: One Vision-Language-Action Model for GUI Visual Agent

Reference 30

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:42.283887Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:42.283887Z digest=sha256:08b625a98b824f9d182a713a0ef66c08694f98f50ad1ca24022c4311c2886a1e

Observation 4f503664-42e3-4ec9-b47e-323d777e7c9e · outbound

This paper cites What can rl bring to vla generalization? an empirical study, 2026.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL What can rl bring to vla generalization? an empirical study, 2026

Reference 31

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:42.356008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:42.356008Z digest=sha256:dfe607a36e1f282269a2ca8c710fc72e3681a69b855df66998e1aeeaf937e76b

Observation 17283d8a-d012-4ebb-bf77-53c42546aa3a · outbound

This paper cites AutoGLM: Autonomous Foundation Agents for GUIs.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL AutoGLM: Autonomous Foundation Agents for GUIs

Reference 32

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:42.436786Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:42.436786Z digest=sha256:b405860ec34f9d886eb2af62691448f038e19dd8404eda3c75ef849ddc361e80

Observation 50122f9e-3853-4e02-896a-7b9e06661d69 · outbound

This paper cites Visualagentbench: Towards large multimodal models as visual foundation agents.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Visualagentbench: Towards large multimodal models as visual foundation agents

Reference 33

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:42.537299Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:42.537299Z digest=sha256:f4ea52466f06028df1744d1aa37d96783fc8b327507ebab64cc1846655fab769

Observation 33949333-e356-4668-90e5-8f2d3bb69805 · outbound

This paper cites Infigui-g1: Advancing gui grounding with adaptive exploration policy optimization.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Infigui-g1: Advancing gui grounding with adaptive exploration policy optimization

Reference 34

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:42.639823Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:42.639823Z digest=sha256:6cd77b81d80b566716dfe913cc6585f66642a1c7773fbda820c0af2a4e03c847

Observation 9b4d659e-65ec-4dd9-a7c8-8fc87ecd151b · outbound

This paper cites Scalecua: Scaling open-source computer use agents with cross-platform data.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Scalecua: Scaling open-source computer use agents with cross-platform data

Reference 35

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:42.708422Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:42.708422Z digest=sha256:3e3941dbbe4289d16c96a7113fea4d62f732ad4f33ea144e3d74faf580f747fe

Observation d545fa2c-f017-495e-8626-1012b854356c · outbound

This paper cites Understanding R1-Zero-Like Training: A Critical Perspective.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Understanding R1-Zero-Like Training: A Critical Perspective

Reference 36

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:42.815891Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:42.815891Z digest=sha256:0a59a64e5bbcdf9831c157b3714b2d5499146909abc27faf7e2809d1fe30898d

Observation 687ce515-40ee-4ecd-b744-12acbd934150 · outbound

This paper cites GUIOdyssey: A Comprehensive Dataset for Cross-App GUI Navigation on Mobile Devices.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL GUIOdyssey: A Comprehensive Dataset for Cross-App GUI Navigation on Mobile Devices

Reference 37

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:42.885175Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:42.885175Z digest=sha256:d65c3fbaa04cded7551fc344d7bb30c39bb08c140c5246feae711c1e7dc7a59b

Observation 2ec95887-07b3-4f19-a857-2d25c2f5ad04 · outbound

This paper cites UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement Learning.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement Learning

Reference 38

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:42.979477Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:42.979477Z digest=sha256:52b554203bda530d9db125d59f47e9a637ba8d630099152f639e518d5340c984

Observation 8963f312-605f-4b8e-948c-973021682eec · outbound

This paper cites GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agents.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL GUI-R1 : A Generalist R1-Style Vision-Language Action Model For GUI Agents

Reference 39

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:43.072415Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:43.072415Z digest=sha256:b4af6fd1e643c43f721ea225180f0acaf49cc81ad3ba3d67fd7c509319b54dac

Observation 60aed442-2c10-4604-aafa-a6b3f14b8b05 · outbound

This paper cites Gui-360 ^ : A comprehensive dataset and benchmark for computer-using agents, 2025.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Gui-360 ^ : A comprehensive dataset and benchmark for computer-using agents, 2025

Reference 40

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:43.171075Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:43.171075Z digest=sha256:59a31d40edab373f933856ea1fa798885a1b1e456be65bb4dda7e172c9be9147

Observation 85e8445c-66bc-4476-95b7-24e0a676dc58 · outbound

This paper cites Rodriguez, Montek Kalsi, Nicolas Chapados, M.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Rodriguez, Montek Kalsi, Nicolas Chapados, M

Reference 41

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:43.267652Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:43.267652Z digest=sha256:3560679d6fc0be749b2bb4b97ef4d66f7ef82ebcef037a75f182dc7f95ecb34e

Observation 98da29d5-d781-4c7e-88a4-e6dba02719f9 · outbound

This paper cites GPT-4o System Card.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL GPT-4o System Card

Reference 42

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:43.349369Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:43.349369Z digest=sha256:94469e1334032127ebfe10f1c76e2a8acc694073ef7fb3cabf5d7e43254983df

Observation 469504ba-e137-4376-8b04-4f4ca4ab0282 · outbound

This paper cites Training language models to follow instructions with human feedback.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Training language models to follow instructions with human feedback

Reference 43

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:43.405282Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:43.405282Z digest=sha256:571d8e7c8822755ae44ac56a8702a35a8fd94381b50f2a4a924139765ac3132e

Observation da766005-eba3-446d-90aa-c7327e77d887 · outbound

This paper cites Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents

Reference 44

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:43.482352Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:43.482352Z digest=sha256:4765c1d415b6c72d8b933631c78baf728eeeb732ddfaef36495f5a92725c41c8

Observation 577a560a-e36c-4b7c-91b0-9fe6805dd2df · outbound

This paper cites WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL WebRL: Training LLM Web Agents via Self-Evolving Online Curriculum Reinforcement Learning

Reference 45

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:43.534953Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:43.534953Z digest=sha256:553acf5884e8e97ce01f0afe8eb89c2867a5ad1b9fcf2888dde8adf333adad6f

Observation cfb42c2b-41a8-42cd-841e-751ecb5e11f4 · outbound

This paper cites UI-TARS: Pioneering Automated GUI Interaction with Native Agents.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL UI-TARS: Pioneering Automated GUI Interaction with Native Agents

Reference 47

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:43.670089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:43.670089Z digest=sha256:991d129c464bde2b171c300b562d2b9426cdfeb92e3d989a372d31e73af67422

Observation a5ab4d93-90fd-47ea-b027-de3fe24e80d1 · outbound

This paper cites Android in the wild: a large-scale dataset for android device control.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Android in the wild: a large-scale dataset for android device control

Reference 48

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:43.724241Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:43.724241Z digest=sha256:e94c866b2186081939d213ba379c382bb535dcb4b9b02191982d2ac3baba3838

Observation ab889816-6b89-4eac-8042-9421659a9d06 · outbound

This paper cites Androidworld: A dynamic benchmarking environment for autonomous agents.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Androidworld: A dynamic benchmarking environment for autonomous agents

Reference 49

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:43.788162Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:43.788162Z digest=sha256:e22448a44369aa22914bbb77db57f27d02ebd5ee867ba09876d43741da94bd8a

Observation 705e1b13-423c-429d-a2ac-67b2f46612d0 · outbound

This paper cites DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:43.830923Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:43.830923Z digest=sha256:7b0354bff67e1d1d80ae601751b85c5ec4be64e675f0ea422c831c028cb57c8b

Observation 8a936a0d-0f04-4903-9915-1d175039698a · outbound

This paper cites OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL OS-Genesis: Automating GUI Agent Trajectory Construction via Reverse Task Synthesis

Reference 51

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:43.957635Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:43.957635Z digest=sha256:1f36e34ee14b23c2557d3c1bd8fd524cc365c7c8ba1344388800ffe0184627d3

Observation 37e2c66c-84cb-4965-84a3-2ebdf66a680f · outbound

This paper cites GUI-G$^2$: Gaussian Reward Modeling for GUI Grounding.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL GUI-G$^2$: Gaussian Reward Modeling for GUI Grounding

Reference 52

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:44.048532Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:44.048532Z digest=sha256:ea9555e7a14935557063217ef6f89e059a344a2ad0d5c478dd75dbbecf4d7cc2

Observation 3b732d0d-0c29-4eba-98fa-75812375cd22 · outbound

This paper cites UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning

Reference 53

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:44.108333Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:44.108333Z digest=sha256:3deb1466d2d0fa6840adf8123b1fa8b2bb4f4199834657d262a49cf91046fd47

Observation 52d685bc-6f57-463e-b576-c32b2849a8da · outbound

This paper cites Think or not? selective reasoning via reinforcement learning for vision-language models.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Think or not? selective reasoning via reinforcement learning for vision-language models

Reference 54

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:44.187749Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:44.187749Z digest=sha256:7623dd52f196d16a69a79148b2e50bb8801858220d6e6f7332795bcc88c9ce55

Observation 6fdf11e7-a310-4aab-96a4-1d102e6ba8b0 · outbound

This paper cites Vagen: Reinforcing world model reasoning for multi-turn vlm agents, 2025 c.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Vagen: Reinforcing world model reasoning for multi-turn vlm agents, 2025 c

Reference 55

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:44.245492Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:44.245492Z digest=sha256:08949d2c93b09c64164f5cac832c7ef9ee8ca649deeda4c32796d4192c4a3394

Observation 88e2232c-5d4c-4c01-8590-a3905c01e98f · outbound

This paper cites Open CUA : Open foundations for computer-use agents.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Open CUA : Open foundations for computer-use agents

Reference 56

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:44.294692Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:44.294692Z digest=sha256:198608129042d96a664a3f065d8b670340c4465618a83c43b8732dc0fbf86a7c

Observation f7106de7-e6a0-43d1-bc18-be09eb504468 · outbound

This paper cites Aligning Large Language Models with Human: A Survey.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Aligning Large Language Models with Human: A Survey

Reference 57

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:44.365668Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:44.365668Z digest=sha256:83fa01b6a27a0a2feabf4c55ec523ebea79f3b0a74aaa4ff0857966d4dc57894

Observation f81078ce-e2ed-4224-ab73-697f1150e41b · outbound

This paper cites Webui: A dataset for enhancing visual ui understanding with web semantics.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Webui: A dataset for enhancing visual ui understanding with web semantics

Reference 58

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:44.432190Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:44.432190Z digest=sha256:64d7ac5f9e96cbc4db7939c363aac8c3b969b42fa817c36c44029d7c5c4ea536

Observation 151c1528-593a-4f64-9f35-062df349735e · outbound

This paper cites GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL GUI-Actor: Coordinate-Free Visual Grounding for GUI Agents

Reference 59

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:44.479478Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:44.479478Z digest=sha256:777e27d11570a53f2aadf682eb7ebb42c7e855939d2c460550eeaa330f920a4f

Observation 1b01d2f5-5e8a-434f-945c-a6eafd4940db · outbound

This paper cites OS-ATLAS: A Foundation Action Model for Generalist GUI Agents.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL OS-ATLAS: A Foundation Action Model for Generalist GUI Agents

Reference 60

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:44.528884Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:44.528884Z digest=sha256:62b7fb8f44b21e2df3f540731f53723c6a9bf55eb72a65747c5ad23552561ba6

Observation 26b3dd2b-62c5-4a2f-b89c-4c1e6cf95440 · outbound

This paper cites OS - ATLAS : Foundation action model for generalist GUI agents.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL OS - ATLAS : Foundation action model for generalist GUI agents

Reference 61

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:44.598785Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:44.598785Z digest=sha256:75a5390bdd7cd2b09454eff7c71758b48e893c1427f754a37eb05a8d9925f0e2

Observation 204c913d-998c-4b24-be91-9544e9954814 · outbound

This paper cites Scaling computer-use grounding via user interface decomposition and synthesis, 2025.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Scaling computer-use grounding via user interface decomposition and synthesis, 2025

Reference 62

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:44.685008Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:44.685008Z digest=sha256:8122b4ff85e7f417e0d3ff4dd730e782fb9dbc75f40aca25c72f6c00260b2ec3

Observation 9373532d-b9f6-41f4-9d86-ef4aa26521a9 · outbound

This paper cites Agenttrek: Agent trajectory synthesis via guiding replay with web tutorials.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Agenttrek: Agent trajectory synthesis via guiding replay with web tutorials

Reference 63

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:44.747371Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:44.747371Z digest=sha256:851f949c18982360d89c6caa53006f9064bf91cca6b4d212210428456d513e76

Observation 32d351d7-7f8a-414a-9c0d-082eb35f7317 · outbound

This paper cites AgentTrek: Agent Trajectory Synthesis via Guiding Replay with Web Tutorials.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL AgentTrek: Agent Trajectory Synthesis via Guiding Replay with Web Tutorials

Reference 64

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:44.793620Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:44.793620Z digest=sha256:2fd4f1fbbb91f78cc15461bf136248f2e929b880282f6a0786b8ca2e40ddf77d

Observation b61f86d4-45e2-4fad-9ca9-8bd250199690 · outbound

This paper cites Aguvis: Unified pure vision agents for autonomous GUI interaction.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Aguvis: Unified pure vision agents for autonomous GUI interaction

Reference 65

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:44.962555Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:44.962555Z digest=sha256:62e0438e8ea1b5e33deccc00716ec80905c69c775920e787602dc3b79fd62be0

Observation 38177d91-8fc9-4041-81a0-6e446cd62a35 · outbound

This paper cites An illusion of progress? assessing the current state of web agents.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL An illusion of progress? assessing the current state of web agents

Reference 66

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:45.035019Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:45.035019Z digest=sha256:0c9d4ca9939d1b178291bffe2ac38caed7935614c2b9d15d6acc01358cd0b2fe

Observation 8c51f430-dbfb-4d11-b26b-06a947c88010 · outbound

This paper cites PixelWeb: The First Web GUI Dataset with Pixel-Wise Labels.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL PixelWeb: The First Web GUI Dataset with Pixel-Wise Labels

Reference 67

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:45.176089Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:45.176089Z digest=sha256:1e38625b0c7a3dde3edf8d1a0453b9405bbc25bf5784dd0848b96f68891e13de

Observation 87390374-c43c-4d16-b791-f56a6902f11e · outbound

This paper cites Regularizing hidden states enables learning generalizable reward model for llms.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Regularizing hidden states enables learning generalizable reward model for llms

Reference 68

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:45.292094Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:45.292094Z digest=sha256:8139f07426f3f5d9250a4317ab4f089c0ad07948768e858cb562eb4f9ddb0fe2

Observation e0b42742-611c-422a-8e2c-7ff795a6b75d · outbound

This paper cites Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Rewards-in-Context: Multi-objective Alignment of Foundation Models with Dynamic Preference Adjustment

Reference 69

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:45.443374Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:45.443374Z digest=sha256:66c612534f779cc98377ca0d2b29107bf457d158431b7aef6fd35e38ee54c58c

Observation 599cc278-1405-46a6-bcdc-52e4c5c562fa · outbound

This paper cites GTA1: GUI Test-time Scaling Agent.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL GTA1: GUI Test-time Scaling Agent

Reference 70

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:45.581241Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:45.581241Z digest=sha256:bff7ade7819d8a89ea354674eb6872154655c0fc29e381619f2f92d98b7c03d6

Observation f6ed61cb-cf8c-408a-9580-41ff07dce058 · outbound

This paper cites Aria-UI: Visual Grounding for GUI Instructions.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Aria-UI: Visual Grounding for GUI Instructions

Reference 71

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:45.689795Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:45.689795Z digest=sha256:a3a11a4d81aeb31461ded79847347e124af689bd27b9e2a837f48ff7bd04af7b

Observation 71647ddb-11e1-48db-ae83-7741d18085b3 · outbound

This paper cites Ferret-ui lite: Lessons from building small on-device gui agents, 2025 c.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Ferret-ui lite: Lessons from building small on-device gui agents, 2025 c

Reference 72

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:45.746543Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:45.746543Z digest=sha256:f588af0f9e2cbd003493fdc5d22fa6b3d1b201d1ecb72c4fb09c76f8ff5c696e

Observation d58c2c67-89e2-45ae-89b2-5b3a2f70efd4 · outbound

This paper cites DAPO: An Open-Source LLM Reinforcement Learning System at Scale.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL DAPO: An Open-Source LLM Reinforcement Learning System at Scale

Reference 73

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:45.825148Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:45.825148Z digest=sha256:c9810fce6daecc36effec7ba9a96b636bcbb830062547a4db0e560f2284c7d54

Observation 35288331-b6b7-471c-92c2-4973e245f65b · outbound

This paper cites Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning

Reference 74

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:45.970836Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:45.970836Z digest=sha256:564a683be02037122ac5d6fff4b1b9ef2ba74fffdd05a4614e25567463ee0ea6

Observation 6bb19ecd-e214-40df-bda9-927fcc3177b9 · outbound

This paper cites Visual backdoor attacks on mllm embodied decision making via contrastive trigger learning.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Visual backdoor attacks on mllm embodied decision making via contrastive trigger learning

Reference 75

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:46.137969Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:46.137969Z digest=sha256:47f7e607a253d6e65d087d079047057cc100374fd377cece37623e5f4eb69a60

Observation ece36221-3a4f-4b8c-958c-ebb3e9f26c90 · outbound

This paper cites Tongui: Internet-scale trajectories from multimodal web tutorials for generalized gui agents.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Tongui: Internet-scale trajectories from multimodal web tutorials for generalized gui agents

Reference 76

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:46.309031Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:46.309031Z digest=sha256:1f75d000fe0d64a6c7da9b0d60dd34e2d2a9c931e0df4ecb908ba7b68b90fc08

Observation a161721e-2ce0-42a5-99e2-acd0982487d8 · outbound

This paper cites Android in the zoo: Chain-of-action-thought for GUI agents.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Android in the zoo: Chain-of-action-thought for GUI agents

Reference 77

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:46.419042Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:46.419042Z digest=sha256:e2c13c267e220d106dec7e7842f0694c61ebfb1b97aef957239a6805aad94393

Observation cd77b6ba-29ef-4761-a3df-410a882af35c · outbound

This paper cites Agent Learning via Early Experience.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Agent Learning via Early Experience

Reference 78

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:46.531155Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:46.531155Z digest=sha256:a8ae0005532b651322b4a6a1ff98157ffd9fddd43a92984a6e207d51f311458d

Observation b3853c00-df93-4e19-926b-f4e2304c78bd · outbound

This paper cites Phi-Ground Tech Report: Advancing Perception in GUI Grounding.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Phi-Ground Tech Report: Advancing Perception in GUI Grounding

Reference 79

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:46.702023Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:46.702023Z digest=sha256:d3d0e419105b05aa78862c82134e97b290c48556c0e603d05f9206735803cedb

Observation 285b02d5-c71e-4438-a921-c6380e2f52e7 · outbound

This paper cites Gpt-4v(ision) is a generalist web agent, if grounded.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Gpt-4v(ision) is a generalist web agent, if grounded

Reference 80

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:46.816068Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:46.816068Z digest=sha256:34e468cad0d62bff679400302457fe93e60460490c85bb575d96e95c388c0a9f

Observation a8b201de-bd34-49f2-b9d9-4132c04b2381 · outbound

This paper cites Group Sequence Policy Optimization.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Group Sequence Policy Optimization

Reference 81

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:46.984573Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:46.984573Z digest=sha256:f8d05f12ecf4d73e98d41adea57cd67a722337b4b831d4622e09b3ae7332b2d9

Observation 6c1a5554-f289-4a61-9fcd-82564176e021 · outbound

This paper cites Agentstudio: A toolkit for building general virtual agents.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Agentstudio: A toolkit for building general virtual agents

Reference 82

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:47.151666Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:47.151666Z digest=sha256:ec73d7ccff32dc893b86010a3c0ab4e408c82d7c66ab7efd149df46fcb5b5630

Observation 7b6c9c2b-9b4a-4957-b353-8ef718aae715 · outbound

This paper cites Mai-ui technical report: Real-world centric foundation gui agents, 2025 a.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Mai-ui technical report: Real-world centric foundation gui agents, 2025 a

Reference 83

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:47.290897Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:47.290897Z digest=sha256:a0b757c5721324b1b845df5eb0881ab2557a4ac0dca6beb72c9400c15e5f0a06

Observation c57c4d58-25f5-46f9-bc14-d967a42a6389 · outbound

This paper cites GUI -g1: Understanding r1-zero-like training for visual grounding in GUI agents.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL GUI -g1: Understanding r1-zero-like training for visual grounding in GUI agents

Reference 84

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:47.423910Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:47.423910Z digest=sha256:2eddbadae2acbcbcdc94d6c82be871da5425d983352ffa778faa0cb69428b8c0

Observation 341ab263-3c83-46e2-a92b-87ab60340fd9 · outbound

This paper cites The surprising effectiveness of negative reinforcement in llm reasoning.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL The surprising effectiveness of negative reinforcement in llm reasoning

Reference 85

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:47.577721Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:47.577721Z digest=sha256:30fb3766c5e21dc555361afbd882c4540fc105430256beacfc5c7d8166f5edc6

Observation 41beed27-bdfd-40b9-8693-56a000e3e5ca · outbound

This paper cites @esa (Ref.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL @esa (Ref

Reference 86

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:47.678442Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:47.678442Z digest=sha256:d4afc1b50c4f21c1a72b0116e9674b0ad8c9280ac62dd757bbc2460d43c71bce

Observation e82a9078-9abe-4a90-aa4a-e541f43612cc · outbound

This paper cites an unresolved cited work.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL Unresolved cited work

Reference 87

Resolution
unresolved
no resolver link, observed 2026-08-02T20:51:47.820096Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:47.820096Z digest=sha256:8a2b84586618190666f494ae8ff0610c0ff4c468c23aff4a5923ad338888a783

Observation d9a6117f-4095-41d1-a051-37a428e0ef82 · outbound

This paper cites point_2d.

GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL point_2d

Reference 88

Resolution
malformed identifier
no resolver link, observed 2026-08-02T20:51:47.961506Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=arxiv_source observed=2026-08-02T20:51:47.961506Z digest=sha256:900e2b86a0d84686bef4905f5402f327025a2cf6bb7aa6830db2c73ab0e79487

Pith citing papers

Observation 1e511dae-b2d1-43db-bfcb-deab746942b6 · inbound

How Mobile World Model Guides GUI Agents? cites this paper.

How Mobile World Model Guides GUI Agents? GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL

Reference 5

Resolution
verified exact
arxiv_id, observed 2026-05-27T02:04:34.683381Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-05-12T04:28:34.562344Z digest=sha256:0c8d3ddb38026bf3a50f0a4da36154f78be561f842b2c75d7481cbf91baa56c8

Observation ea4cfdd9-3dc1-41ff-b989-de3720d63a17 · inbound

How Mobile World Model Guides GUI Agents? cites this paper.

How Mobile World Model Guides GUI Agents? GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL

Reference 5

Resolution
verified exact
arxiv_id, observed 2026-05-27T02:04:34.683381Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-05-25T06:00:34.560405Z digest=sha256:afba476cbff1640effdc3c76f08f5b5d428b24accdfbd65f77796c0a0aa4c512

Observation 64b3bdc3-82c7-4ed2-8889-7e699ce8bea5 · inbound

Learning Agentic Policy from Action Guidance cites this paper.

Learning Agentic Policy from Action Guidance GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL

Reference 69

Resolution
verified exact
arxiv_id, observed 2026-05-27T02:04:34.683381Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-05-13T05:02:49.206053Z digest=sha256:08fd22195789064cc2105088041e2403ed7f8bbf2041d95c3cb6921793db2a45

Observation f1b5459a-a756-4a70-8539-8895bc52b352 · inbound

PAGER: Bridging the Semantic-Execution Gap in Point-Precise Geometric GUI Control cites this paper.

PAGER: Bridging the Semantic-Execution Gap in Point-Precise Geometric GUI Control GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL

Reference 45

Resolution
verified exact
arxiv_id, observed 2026-05-27T02:04:34.683381Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=pdf_text observed=2026-05-20T18:46:20.417039Z digest=sha256:688218113734af238a74705c21d5222e15737e67b9d2dadd25178ee598020976

Observation 92b083bd-e12e-4610-81c9-8bebf8d79f9e · inbound

AsyncWebRL: Efficient Asynchronous Reinforcement Learning for Multi-Step Visual Web Agents cites this paper.

AsyncWebRL: Efficient Asynchronous Reinforcement Learning for Multi-Step Visual Web Agents GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL

Reference 10

Resolution
metadata mismatch
local_arxiv, observed 2026-07-02T11:56:55.517715Z

Source-reported events for the cited work

No event found in the named queried sources as of 2026-08-12T06:34:41.77262+00:00.

source=arxiv_source observed=2026-06-28T02:45:25.694378Z digest=sha256:20909b1d00b87ffd3ed99cf93974a8c44332b91f518201d0be23a9faa4bfa616

Observation 82ca7d81-97da-4b9f-ba93-b2be6818571f · inbound

SportsGrounder: Proposal-Aided Interleaved Grounding for Dense Sports Video Reasoning cites this paper.

SportsGrounder: Proposal-Aided Interleaved Grounding for Dense Sports Video Reasoning GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL

Reference 50

Resolution
unresolved
no resolver link, observed 2026-08-12T00:44:22.198316Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-12T00:44:22.198316Z digest=sha256:c69e4de86868b6a8d02535f7ec8d9034c2a12dc25780454b8573564d9a6fea7d

Observation 0b4ac350-6ea5-4f09-9410-f3717e958cbc · inbound

Software Engineering for and with GUI Agent cites this paper.

Software Engineering for and with GUI Agent GUI-Libra: Training Native GUI Agents to Reason and Act with Action-aware Supervision and Partially Verifiable RL

Reference 300

Resolution
unresolved
no resolver link, observed 2026-08-11T20:19:16.243585Z

Source-reported events for the cited work

Unavailable: canonical work link unavailable.

source=pdf_text observed=2026-08-11T20:19:16.243585Z digest=sha256:b0c131287c49ac5c204c7648941ba955e76533097ab90b0c7ab6c8d4a5703454